{"id":"https://openalex.org/W4415539746","doi":"https://doi.org/10.1145/3746027.3754753","title":"Unsupervised Similarity-Fusion Transformer Hashing for Multimodal Retrieval","display_name":"Unsupervised Similarity-Fusion Transformer Hashing for Multimodal Retrieval","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415539746","doi":"https://doi.org/10.1145/3746027.3754753"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754753","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754753","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057461144","display_name":"Zhan Yang","orcid":"https://orcid.org/0000-0002-6336-0228"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhan Yang","raw_affiliation_strings":["Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-6336-0228","affiliations":[{"raw_affiliation_string":"Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001605143","display_name":"Binghong Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Binghong Chen","raw_affiliation_strings":["Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0006-6688-6918","affiliations":[{"raw_affiliation_string":"Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033444023","display_name":"Jiajun Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiajun Tang","raw_affiliation_strings":["Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0003-0130-150X","affiliations":[{"raw_affiliation_string":"Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100599400","display_name":"Yinan Li","orcid":"https://orcid.org/0000-0002-3300-8098"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinan Li","raw_affiliation_strings":["Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-3300-8098","affiliations":[{"raw_affiliation_string":"Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139660479"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5932","last_page":"5941"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9922000169754028,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9901999831199646,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.6814000010490417},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4936999976634979},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49160000681877136},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.46889999508857727},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.3610999882221222},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.357699990272522},{"id":"https://openalex.org/keywords/feature-hashing","display_name":"Feature hashing","score":0.35409998893737793},{"id":"https://openalex.org/keywords/thresholding","display_name":"Thresholding","score":0.3433000147342682},{"id":"https://openalex.org/keywords/dynamic-perfect-hashing","display_name":"Dynamic perfect hashing","score":0.31189998984336853}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7501999735832214},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6814000010490417},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5706999897956848},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4936999976634979},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49160000681877136},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.46889999508857727},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4223000109195709},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.3610999882221222},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.357699990272522},{"id":"https://openalex.org/C133667856","wikidata":"https://www.wikidata.org/wiki/Q5439682","display_name":"Feature hashing","level":5,"score":0.35409998893737793},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.3433000147342682},{"id":"https://openalex.org/C122907437","wikidata":"https://www.wikidata.org/wiki/Q5318999","display_name":"Dynamic perfect hashing","level":5,"score":0.31189998984336853},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.3021000027656555},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3003999888896942},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.29829999804496765},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.28700000047683716},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.2538999915122986},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754753","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754753","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4020270610","display_name":null,"funder_award_id":"62202501","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2006147162","https://openalex.org/W3014701888","https://openalex.org/W3017133364","https://openalex.org/W3033740891","https://openalex.org/W3122091215","https://openalex.org/W3133715405","https://openalex.org/W4200632612","https://openalex.org/W4220857054","https://openalex.org/W4375801803","https://openalex.org/W4389319187","https://openalex.org/W4391917913","https://openalex.org/W4395663526","https://openalex.org/W4402811055","https://openalex.org/W4404454982","https://openalex.org/W4406094085"],"related_works":[],"abstract_inverted_index":{"Unsupervised":[0,69],"hashing":[1,178],"is":[2,94,121,141],"applied":[3],"in":[4,26,129],"large-scale":[5],"multimodal":[6,74],"retrieval":[7,20,27,60],"by":[8],"mapping":[9],"original":[10],"data":[11],"from":[12],"heterogeneous":[13,127],"modalities":[14,128],"into":[15],"compact":[16],"binary":[17],"codes.":[18],"Transformer-based":[19,118],"augmented":[21],"generation":[22],"possesses":[23],"significant":[24],"advantages":[25],"accuracy":[28],"and":[29,49,91,156,167],"context-awareness,":[30],"yet":[31],"faces":[32],"scalability":[33],"challenges":[34],"due":[35],"to":[36,96,143,176],"the":[37,44,80,130,137,171],"computational":[38],"overhead":[39],"of":[40,46,126,174],"dense":[41],"embedding.":[42],"Thus,":[43],"integration":[45,125],"hash":[47,146],"learning":[48],"Transformer":[50,71],"provides":[51],"a":[52,67,98,153],"feasible":[53],"improvement":[54],"scheme,":[55],"which":[56],"can":[57,108],"achieve":[58,157],"efficient":[59],"preserving":[61],"semantic":[62,104],"association.":[63],"This":[64],"paper":[65],"proposes":[66],"novel":[68],"Similarity-Fusion":[70],"Hashing":[72],"for":[73],"retrieval,":[75],"denoted":[76],"as":[77],"USFTH.":[78],"Initially,":[79],"modal":[81],"fusion":[82,139],"similarity":[83,100,131],"matrix":[84,132],"based":[85],"on":[86,164],"Gaussian":[87],"kernel,":[88],"sigmoid":[89],"function,":[90],"Laplacian":[92],"transformation":[93],"introduced":[95],"construct":[97],"discriminative":[99],"matrix,":[101],"ensuring":[102],"that":[103,145],"correlation":[105],"among":[106],"samples":[107],"be":[109],"captured":[110],"precisely.":[111],"Then,":[112],"cross-modal":[113],"multiplex":[114],"joint":[115],"construction":[116],"via":[117],"attention":[119],"mechanisms":[120],"designed,":[122],"realizing":[123],"effective":[124],"through":[133],"multi-path":[134],"fusion.":[135],"Furthermore,":[136],"consensus":[138],"strategy":[140],"proposed":[142],"ensure":[144],"codes":[147],"generated":[148],"under":[149],"unsupervised":[150],"conditions":[151],"possess":[152],"uniform":[154],"distribution":[155],"accurate":[158],"retrieval.":[159],"In":[160],"addition,":[161],"comprehensive":[162],"experiments":[163],"MIRFlickr,":[165],"NUS-WIDE,":[166],"IAPR-TC12":[168],"datasets":[169],"demonstrate":[170],"superior":[172],"performance":[173],"USFTH":[175],"state-of-the-art":[177],"approaches.":[179]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}